Observability for LangServe with Opik

LangServe does not define its own standalone OpenTelemetry bootstrap. Instrumentation is configured at the host app/runtime layer (typically FastAPI + LangChain components).

When this guide applies

Use this when your LangServe routes run inside a Python web app and you want request + framework spans in Opik.

Opik OTLP endpoint modes

For full endpoint/header details, see Opik OpenTelemetry overview.

$
export OTEL_EXPORTER_OTLP_ENDPOINT=https://www.comet.com/opik/api/v1/private/otel
$
export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=<your-workspace>,projectName=<your-project-name>'

OTEL configuration pattern for LangServe

Intent: Configure telemetry at the LangServe host boundary so request and framework spans can be exported.

Applies when: LangServe is mounted in an app you control (for example FastAPI).

Required inputs:

• host runtime instrumentation enabled
• OTLP endpoint
• OTLP headers for your deployment mode

Optional inputs:

• explicit service.name
• additional framework or library instrumentors
• route-level filtering/sampling

Minimal valid setup:

• set OTEL_EXPORTER_OTLP_ENDPOINT
• set OTEL_EXPORTER_OTLP_HEADERS
• enable instrumentation for your host app and LangChain stack

Use canonical host/runtime setup from:

• OpenTelemetry FastAPI instrumentation
• Opik LangChain integration guide

Validation

1. Send a request through a LangServe endpoint.
2. Confirm a root HTTP/server span is emitted from your host app.
3. Confirm downstream LangChain/LangServe-related spans are exported and visible in Opik.

Source references

• LangServe repository
• OpenTelemetry FastAPI instrumentation
• Opik LangChain integration guide
• Opik OpenTelemetry overview